Change8

v0.30.2

📦 ollamaView on GitHub →
3 features🐛 7 fixes🔧 5 symbols

Summary

This release introduces support for Cline CLI and Qwen integration, alongside numerous stability improvements and fixes related to llama-server and model loading.

✨ New Features

  • Show and auto-install Cline CLI.
  • Add Qwen code integration to cmd/launch.
  • Add laguna (poolside) architecture support via a llama.cpp patch.

🐛 Bug Fixes

  • Fix opencode local model limits in launch.
  • Include cached prompt tokens in llama-server counts.
  • Harden app markdown URL handling (multiple fixes).
  • Allow Radeon 8060S iGPU by default in discover.
  • Detect llama-server load stalls from output.
  • Ignore llama-server SSE ping comments.
  • Fix laguna patch build breakage.

Affected Symbols